Project: Baby names

Project weight: 10 points

Database of baby names

The United States Social Security Administration maintains records of babies born in the USA each year. Historical data of first names of babies is available on the Social Security website. It provides the number of babies registered with a given first name in a given year. Here is a sample data for the year 1960:

Another data set provides the number of babies registered with a given first name in each US state. Here is a sample of data for New York:

Objectives

Download the files with baby names data:

names.zip - cumulative US data
namesbystate.zip - baby names by state

Analyze some facets of this data. You can use one of the data sets (national or state data), or both.

Here are some possible topics you can pursue:

  • Name diversity. How many names were used each year? How many babies shared the same name on average? How did this change over the years? How does this differ among various states? How does this differ depending on the gender of babies?

  • Name popularity. Which names are most and least popular? How has the popularity of various names been changing over the years? Are names popular in one state also popular in other states? What fraction of babies are given, say, one of the one hundred most popular names, and what fraction are given very unique names? Does this depend on the gender of babies? Are there sudden spikes of the popularity of some names?

  • Gender specificity. Some names are given only to male babies, some only to female babies, and some are given to both males and females. What fraction of names belong to each of these groups? Does this differ depending on the year and state? For names given to both males and females, how can you measure if a name is predominantly male or female? Does such a measure vary by state? Are there names that over the years evolved from being predominantly male to predominantly female and vice versa?

  • Name history. What was the first year that a given name appeared in the data? Did some names appear in some states much later than in other states? What names have been used for many years and what names were in use only for a few years? What fraction of names fall into each category? Does this depend on state and gender? Are there names that disappear for several years and then appear again?

  • Anything else you find interesting.